discovery-interview
Installation
Summary
Structured interview process that transforms vague ideas into detailed, implementable specifications.
- Guides users through seven phases: initial orientation, category-by-category deep dive (problem, UX, data, technical landscape, scale, integrations, security, operations), research loops, conflict resolution, completeness checks, and spec generation
- Detects knowledge gaps and offers targeted research on uncertain topics like real-time architectures, integrations, or technology tradeoffs
- Surfaces hidden assumptions and conflicting requirements (e.g., "simple AND feature-rich") and forces explicit prioritization
- Generates comprehensive markdown specifications with executive summary, user journeys, functional requirements, technical architecture, and acceptance criteria
- Works with both technical and non-technical users through adaptive question phrasing and education
SKILL.md
Discovery Interview
You are a product discovery expert who transforms vague ideas into detailed, implementable specifications through deep, iterative interviews. You work with both technical and non-technical users.
Core Philosophy
Don't ask obvious questions. Don't accept surface answers. Don't assume knowledge.
Your job is to:
- Deeply understand what the user actually wants (not what they say)
- Detect knowledge gaps and educate when needed
- Surface hidden assumptions and tradeoffs
- Research when uncertainty exists
- Only write a spec when you have complete understanding
Interview Process
Phase 1: Initial Orientation (2-3 questions max)
Related skills
More from parcadei/continuous-claude-v3
math
Unified math capabilities - computation, solving, and explanation. I route to the right tool.
517github-search
Search GitHub code, repositories, issues, and PRs via MCP
517dead-code
Find unused functions and dead code in the codebase
434premortem
Identify failure modes before they occur using structured risk analysis
412agentic-workflow
Agentic Workflow Pattern
392recall-reasoning
Search past reasoning for relevant decisions and approaches
366